ai-chatbot-builder

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests external, user-provided content for RAG (e.g., "PDF 문서를 학습해서 답변해주는 챗봇" and "지식베이스(RAG): 벡터 데이터베이스") and also describes external channel integrations (Slack, Discord, Telegram), meaning the agent will read and interpret untrusted/user-generated third‑party content at runtime.